WonderZoom: Multi-Scale 3D World Generation
Jin Cao, Hong-Xing Yu, Jiajun Wu
Abstract
We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challenge is the lack of a scale-aware 3D representation capable of generating and rendering content with largely different spatial sizes. WonderZoom addresses this through two key innovations: (1) scale-adaptive Gaussian surfels for generating and real-time rendering of multi-scale 3D scenes, and (2) a progressive detail synthesizer that iteratively generates finer-scale 3D contents. Our approach enables users to ``zoom into'' a 3D region and auto-regressively synthesize previously non-existent fine details from landscapes to microscopic features. Experiments demonstrate that WonderZoom significantly outperforms state-of-the-art video and 3D models in both quality and alignment, enabling multi-scale 3D world creation from a single image. We show video results and an interactive viewer of generated multi-scale 3D worlds on the website of the supplementary materials.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on33
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Alias-Free Generative Adversarial NetworksTero Karras, Miika Aittala, Samuli Laine, Erik Härkönen et al.NeurIPS 2021 · 2,126 citations
Related papers
- GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic GuidanceJiale Shi, Jiarui Hu, Zesong Yang, Kaixuan Luan et al.CVPR 2026
- FlexWorld: Progressively Expanding 3D Scenes for Flexible-View ExplorationLuxi Chen, Zihan Zhou, Min Zhao, Yikai Wang et al.NeurIPS 2025 · 7 citations
- Arbitrary-Scale 3D Gaussian Super-ResolutionHuimin Zeng, Yue Bai, Yun FuAAAI 2026 · 2 citations
- MS3D: High-Quality 3D Generation via Multi-Scale Representation ModelingGuan Luo, Jianfeng ZhangICCV 2025 · 1 citation
- Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian SurfelsYikai Wang, Xinzhou Wang, Zilong Chen, Zhengyi Wang et al.NeurIPS 2024 · 40 citations
